def test_default():
data = load_breast_cancer()
variable_names = data.feature_names
df = pd.DataFrame(data.data, columns=variable_names)
df["target"] = data.target
binning_process = BinningProcess(variable_names)
estimator = LogisticRegression()
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator).fit(df)
with raises(ValueError):
sct = scorecard.table(style="new")
sct = scorecard.table(style="summary")
sc_min, sc_max = sct.groupby("Variable").agg(
{'Points': [np.min, np.max]}).sum()
assert sc_min == approx(-43.65762593147646, rel=1e-6)
assert sc_max == approx(42.69694657427327, rel=1e-6)
def test_default_continuous():
data = load_boston()
variable_names = data.feature_names
df = pd.DataFrame(data.data, columns=variable_names)
df["target"] = data.target
binning_process = BinningProcess(variable_names)
estimator = LinearRegression()
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator).fit(df)
sct = scorecard.table(style="detailed")
sc_min, sc_max = sct.groupby("Variable").agg(
{'Points': [np.min, np.max]}).sum()
assert sc_min == approx(-15.813545796848476, rel=1e-6)
assert sc_max == approx(85.08156623609487, rel=1e-6)
def buildScoreCard(df, features, labelCol):
binning_process = BinningProcess(features)
estimator = HuberRegressor(max_iter=200)
scorecard = Scorecard(binning_process=binning_process, target=labelCol,
estimator=estimator, scaling_method=None,
scaling_method_params={"min": 0, "max": 100},
reverse_scorecard=True)
scorecard.verbose = True
scorecard.fit(df, check_input=False)
scorecard.information(print_level=2)
print(scorecard.table(style="summary"))
score = scorecard.score(df)
y_pred = scorecard.predict(df)
plt.scatter(score, df[labelCol], alpha=0.01, label="Average profit")
plt.plot(score, y_pred, label="Huber regression", linewidth=2, color="orange")
plt.ylabel("Average profit value (unit=100,000)")
plt.xlabel("Score")
plt.legend()
plt.show()
def test_scaling_method_min_max():
data = load_breast_cancer()
variable_names = data.feature_names
df = pd.DataFrame(data.data, columns=variable_names)
df["target"] = data.target
binning_process = BinningProcess(variable_names)
estimator = LogisticRegression()
scaling_method_params = {"min": 300, "max": 850}
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator, scaling_method="min_max",
scaling_method_params=scaling_method_params).fit(df)
sct = scorecard.table(style="summary")
sc_min, sc_max = sct.groupby("Variable").agg(
{'Points': [np.min, np.max]}).sum()
assert sc_min == approx(300, rel=1e-6)
assert sc_max == approx(850, rel=1e-6)
def test_scaling_method_pdo_odd():
data = load_breast_cancer()
variable_names = data.feature_names
df = pd.DataFrame(data.data, columns=variable_names)
df["target"] = data.target
odds = 1 / data.target.mean()
binning_process = BinningProcess(variable_names)
estimator = LogisticRegression()
scaling_method_params = {"pdo": 20, "odds": odds, "scorecard_points": 600}
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator, scaling_method="pdo_odds",
scaling_method_params=scaling_method_params).fit(df)
sct = scorecard.table(style="summary")
sc_min, sc_max = sct.groupby("Variable").agg(
{'Points': [np.min, np.max]}).sum()
assert sc_min == approx(-612.2266586867094, rel=1e-6)
assert sc_max == approx(1879.4396115559216, rel=1e-6)
def test_rounding():
data = load_breast_cancer()
variable_names = data.feature_names
X = pd.DataFrame(data.data, columns=variable_names)
y = data.target
binning_process = BinningProcess(variable_names)
estimator = LogisticRegression()
scaling_method_params = {"min": 200.52, "max": 850.66}
scorecard = Scorecard(binning_process=binning_process,
estimator=estimator, scaling_method="min_max",
scaling_method_params=scaling_method_params,
rounding=True).fit(X, y)
sct = scorecard.table(style="summary")
sc_min, sc_max = sct.groupby("Variable").agg(
{'Points': [np.min, np.max]}).sum()
assert sc_min == approx(201, rel=1e-6)
assert sc_max == approx(851, rel=1e-6)
def test_rounding_pdo_odds():
data = load_breast_cancer()
variable_names = data.feature_names
X = pd.DataFrame(data.data, columns=variable_names)
y = data.target
odds = 1 / data.target.mean()
binning_process = BinningProcess(variable_names)
estimator = LogisticRegression()
scaling_method_params = {"pdo": 20, "odds": odds, "scorecard_points": 600}
scorecard = Scorecard(binning_process=binning_process,
estimator=estimator, scaling_method="pdo_odds",
scaling_method_params=scaling_method_params,
rounding=True).fit(X, y)
sct = scorecard.table(style="summary")
sc_min, sc_max = sct.groupby("Variable").agg(
{'Points': [np.min, np.max]}).sum()
assert sc_min == approx(-612, rel=1e-6)
assert sc_max == approx(1880, rel=1e-6)